A performance comparison of hand motion EMG classification

Sungtae Shin, Reza Tafreshi, Reza Langari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

Powered prosthesis is of considerable value to amputees to enable them to perform their daily-life activities with convenience. One of applicable control signals for controlling a powered prosthesis is the myoelectric signal. A number of commercial products have been developed that utilize myoelectric control for powered prostheses; however, the functionality of these devices is still insufficient to satisfy the needs of amputees. For the purpose of a comparison, several electromyogram classification methods have been studied in this paper. The performance criteria included not only classification accuracy, but also repeatability and robustness of the classifier, training time for online training performance, and computational time for real-time operation were evaluated with seven classification algorithms. The study included five different feature sets with time-domain feature values and autoregressive model coefficients. In summary, the quadratic discriminant analysis showed a remarkable performance in terms of high classification accuracy, high robustness, and low computational time of training and classification from the experiment results.

Original languageEnglish
Title of host publication2014 Middle East Conference on Biomedical Engineering, MECBME 2014
PublisherIEEE Computer Society
Pages353-356
Number of pages4
ISBN (Print)9781479947997
DOIs
Publication statusPublished - 2014
Event2014 2nd Middle East Conference on Biomedical Engineering, MECBME 2014 - Doha, Qatar
Duration: 17 Feb 201420 Feb 2014

Other

Other2014 2nd Middle East Conference on Biomedical Engineering, MECBME 2014
CountryQatar
CityDoha
Period17/2/1420/2/14

Fingerprint

Discriminant analysis
Prosthetics
Classifiers
Experiments
Prostheses and Implants

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Shin, S., Tafreshi, R., & Langari, R. (2014). A performance comparison of hand motion EMG classification. In 2014 Middle East Conference on Biomedical Engineering, MECBME 2014 (pp. 353-356). [6783276] IEEE Computer Society. https://doi.org/10.1109/MECBME.2014.6783276

A performance comparison of hand motion EMG classification. / Shin, Sungtae; Tafreshi, Reza; Langari, Reza.

2014 Middle East Conference on Biomedical Engineering, MECBME 2014. IEEE Computer Society, 2014. p. 353-356 6783276.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shin, S, Tafreshi, R & Langari, R 2014, A performance comparison of hand motion EMG classification. in 2014 Middle East Conference on Biomedical Engineering, MECBME 2014., 6783276, IEEE Computer Society, pp. 353-356, 2014 2nd Middle East Conference on Biomedical Engineering, MECBME 2014, Doha, Qatar, 17/2/14. https://doi.org/10.1109/MECBME.2014.6783276
Shin S, Tafreshi R, Langari R. A performance comparison of hand motion EMG classification. In 2014 Middle East Conference on Biomedical Engineering, MECBME 2014. IEEE Computer Society. 2014. p. 353-356. 6783276 https://doi.org/10.1109/MECBME.2014.6783276
Shin, Sungtae ; Tafreshi, Reza ; Langari, Reza. / A performance comparison of hand motion EMG classification. 2014 Middle East Conference on Biomedical Engineering, MECBME 2014. IEEE Computer Society, 2014. pp. 353-356
@inproceedings{e42dee5865934a90bdd4dab054c75082,
title = "A performance comparison of hand motion EMG classification",
abstract = "Powered prosthesis is of considerable value to amputees to enable them to perform their daily-life activities with convenience. One of applicable control signals for controlling a powered prosthesis is the myoelectric signal. A number of commercial products have been developed that utilize myoelectric control for powered prostheses; however, the functionality of these devices is still insufficient to satisfy the needs of amputees. For the purpose of a comparison, several electromyogram classification methods have been studied in this paper. The performance criteria included not only classification accuracy, but also repeatability and robustness of the classifier, training time for online training performance, and computational time for real-time operation were evaluated with seven classification algorithms. The study included five different feature sets with time-domain feature values and autoregressive model coefficients. In summary, the quadratic discriminant analysis showed a remarkable performance in terms of high classification accuracy, high robustness, and low computational time of training and classification from the experiment results.",
author = "Sungtae Shin and Reza Tafreshi and Reza Langari",
year = "2014",
doi = "10.1109/MECBME.2014.6783276",
language = "English",
isbn = "9781479947997",
pages = "353--356",
booktitle = "2014 Middle East Conference on Biomedical Engineering, MECBME 2014",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - A performance comparison of hand motion EMG classification

AU - Shin, Sungtae

AU - Tafreshi, Reza

AU - Langari, Reza

PY - 2014

Y1 - 2014

N2 - Powered prosthesis is of considerable value to amputees to enable them to perform their daily-life activities with convenience. One of applicable control signals for controlling a powered prosthesis is the myoelectric signal. A number of commercial products have been developed that utilize myoelectric control for powered prostheses; however, the functionality of these devices is still insufficient to satisfy the needs of amputees. For the purpose of a comparison, several electromyogram classification methods have been studied in this paper. The performance criteria included not only classification accuracy, but also repeatability and robustness of the classifier, training time for online training performance, and computational time for real-time operation were evaluated with seven classification algorithms. The study included five different feature sets with time-domain feature values and autoregressive model coefficients. In summary, the quadratic discriminant analysis showed a remarkable performance in terms of high classification accuracy, high robustness, and low computational time of training and classification from the experiment results.

AB - Powered prosthesis is of considerable value to amputees to enable them to perform their daily-life activities with convenience. One of applicable control signals for controlling a powered prosthesis is the myoelectric signal. A number of commercial products have been developed that utilize myoelectric control for powered prostheses; however, the functionality of these devices is still insufficient to satisfy the needs of amputees. For the purpose of a comparison, several electromyogram classification methods have been studied in this paper. The performance criteria included not only classification accuracy, but also repeatability and robustness of the classifier, training time for online training performance, and computational time for real-time operation were evaluated with seven classification algorithms. The study included five different feature sets with time-domain feature values and autoregressive model coefficients. In summary, the quadratic discriminant analysis showed a remarkable performance in terms of high classification accuracy, high robustness, and low computational time of training and classification from the experiment results.

UR - http://www.scopus.com/inward/record.url?scp=84900807891&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900807891&partnerID=8YFLogxK

U2 - 10.1109/MECBME.2014.6783276

DO - 10.1109/MECBME.2014.6783276

M3 - Conference contribution

AN - SCOPUS:84900807891

SN - 9781479947997

SP - 353

EP - 356

BT - 2014 Middle East Conference on Biomedical Engineering, MECBME 2014

PB - IEEE Computer Society

ER -